repowiserepowise
Sign in
hkuds/rag-anything
OverviewDocsArchitectureKnowledge GraphFilesCode HealthSecurityRefactoring

People & History

CommitsContributorsDecisions
Chat
Stats
repowiserepowise
ExplorePricingDocs
Sign in
repowisehkuds/rag-anything
RA
RA

hkuds / rag-anything

pythonmaina8538ef19.9K linessynced 4mo ago

Code health

4.7out of 10Needs work

This codebase scores 4.7 out of 10 for code health, which we rate needs work. Risk is concentrated, as it usually is: 9 of 59 files are git hotspots, and they average 2.2 — which is where the fixes pay off most.

Full health report →
Score validation13/201.5× baselineTop-ranked files that did go on to need a bug fixDead code30exportsUnused exports that nothing in the graph reaches

Do next

1 thing worth doing this quarter.

Worth planning

  • Delete 1 unused symbol or file (112 lines)

    Nothing in the graph reaches them, across 1 file; every reader and agent pays to skip them.

    symbols
    1
    lines
    112
    safe to delete
    Yes(inferred)
    Small effort

Improve what Repowise can see

  • Add a test coverage report

    Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.

    line coverage
    Unknown, no report
    Small effort
  • Review the 37 proposed decisions

    None is accepted yet, so nothing can drift from one and agents get no enforced guidance from them.

    proposed
    37
    accepted
    0
    Medium effort
Lines of code
19.9K
Files
59
Symbols
481
Modules
6
Languages
1

Recent activity

All commits →

Commits

  • 4d7b65cbstyle: apply ruff-format (v0.6.4) to testparser_kwargs.py4mo ago
  • 6d8357d8Fix MinerU Windows unsafe paths4mo ago
  • ac398b1bfeat: upgrade MiniMax default model to M34mo ago
  • 59f50e18Fix lint after PR merges4mo ago
  • ea3ec1cb🔧 chore(deps): pin lightrag-hku version4mo ago
  • 83956342Update README.md4mo ago

Decisions

  • Optionally replace image paths with base64 for VLM processingproposed
  • Include only specific flags in cache data for query context/prompt needsproposed
  • Hash large multimodal content instead of storing directly in cache dataproposed
  • Use hashed, normalized cache keys for multimodal queriesproposed
  • Address issue where process_document_complete can get stuck due to intermittent network errorsproposed
  • Retry policy targets transient failures in LLM/embedding/network operationsproposed
▸

Everything we found

422 open

Every detector's open count by area, each with its worst example. An inventory, not a to-do list: the actions above are the part worth doing.

  • worst item is critical severity. Code health317Untested hotspot · raganything/parser.py53 findings · 9.1 deducted→
  • worst item is medium severity. Decisions46raganything/parser.py37 awaiting review · 9 hotspots ungoverned→
  • worst item is medium severity. Ownership47raganything/query.py87% single-owner concentration, 5 commits in 90d→
  • worst item is low severity. Dead code12examples/batch_processing_example.pyUnreachable symbol (70 lines)→

Composition

Open the graph →
python 100%

Explore this codebase

  • Docs0 pages across 6 modules→
  • ChatAsk this codebase a question and get an answer with its sources.→
  • Files59 files with per-file docs, health and history→
  • ArchitectureDependency graph, layers, and 1 entry points→
  • Code healthPer-file scores, 331 open findings, coverage and refactoring targets→
  • Knowledge graphEntities, communities, and the paths between them→
  • Change couplingFiles that keep changing together, mined from commit history→
  • CommitsChange-risk ranked history with agent provenance→
  • ContributorsBus factor, per-file maintainers, and the human/agent split→
  • StatsSize class, origin, lifetime churn, rhythm and records→
  • CostsWhat indexing this snapshot cost, by model and by run.→